Skip to content
latestai.eulatestai.eu
L1

Limite 1B Violetto

by Paradigma

1B-parameter model from Paradigma specialized for hard competitive math problems, released with code and weights.

UnverifiedLanguage ModelsResearchModel

Updated EU status checked Last shown

Limite 1B Violetto at a glance

What is Limite 1B Violetto?
Limite 1B Violetto is a model from Paradigma. 1B-parameter model from Paradigma specialized for hard competitive math problems, released with code and weights.
Who makes Limite 1B Violetto?
Limite 1B Violetto is made by Paradigma.
Does Limite 1B Violetto work in the EU?
Unverified. No explicit evidence found. Weights are reportedly downloadable, but the license is unconfirmed and could include regional restrictions (the "LLaMA" name suggests a possible Llama-derived license). Last verified 14 Nov 2026.
How much does Limite 1B Violetto cost?
Open source. Weights reportedly released for free download; unverified.
Where was Limite 1B Violetto shown?
In 1 creator video by AI Search. Most recently by AI Search on 27 Sept 2026, at 31:56 in “Waifus incoming, GPT 6 Sol, Grok 4.7, Opus 5.5, Mimo 2.6, Step 5, OpenMuse: AI NEWS”.

Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.

About

Limite 1B Violetto (also referred to as LLaMA 1B Violetto) is a small language model from Paradigma, with about 1 billion parameters, specialized for hard competitive-level mathematics. No official page could be fetched, so the details here rely on a single creator video summary.

According to that summary, the model scores about 94% on a competitive math benchmark and outperforms much larger models on it. The total download is reported to be around 2 GB, and both code and models are said to have been released. The benchmark name, license, base model and exact release date were not confirmed.

Because of its size, it can likely run on consumer hardware. It is a narrow specialist for math reasoning rather than a general-purpose assistant, and its performance outside that domain is unknown.

Key features
  • About 1B parameters, roughly 2 GB total
  • Specialized for hard competitive math
  • Reported ~94% score, beating much larger models (per creator, unverified)
  • Code and models reportedly released
1 moment

As seen on YouTube

Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.

Keep exploring

Similar AI tools

Closest neighbours by meaning, not just by category.

M1

MiniCPM5 1B

Model · OpenBMB

1

1B-parameter dense open-weights language model from OpenBMB for on-device use, with hybrid thinking and 128K context.

Available in EULanguage Models
21 May 2026Open source
ZG

ZGCM-1

Model

1

Open 7.39B dense model for math reasoning and agentic search, with a 256K context and the full training pipeline released.

Available in EULanguage Models
Sept 2026Open source
B2

Bonsai 27B

Model · PrismML

2

Ternary/1-bit compressed 27B-parameter model from PrismML, about 3.9–5.9 GB, built to run on phones and laptops.

UnverifiedLanguage Models
Release date n/a
MM

MiniMax M3

Model · MiniMax

4

Open-weights native multimodal MoE model from MiniMax, ~428B parameters (~23B active) with 1M-token context.

Available in EULanguage Models
2 Jun 2026Open source
L2

LongCat 2.0

Model · Meituan

1

Meituan's open-weights 1.6T-parameter mixture-of-experts LLM (48B active), aimed at agentic coding and reasoning tasks.

Available in EULanguage Models
Release date n/aOpen source
SP

Spark-X2.6-1.7B

Model

1

Compact 1.7B open-weights text LLM for on-device use, with adjustable thinking levels and English/Chinese support.

Available in EULanguage Models
19 Oct 2026Open source